Skip to main content
YDB is a versatile open source Distributed SQL Database that combines high availability and scalability with strong consistency and ACID transactions. It accommodates transactional (OLTP), analytical (OLAP), and streaming workloads simultaneously.
This notebook shows how to use functionality related to the YDB vector store.

​
Setup

First, set up a local YDB with Docker: 
! docker run -d -p 2136:2136 --name ydb-langchain -e YDB_USE_IN_MEMORY_PDISKS=true -h localhost ydbplatform/local-ydb:trunk
You’ll need to install langchain-ydb to use this integration 
! pip install -qU langchain-ydb

​
Credentials

There are no credentials for this notebook, just make sure you have installed the packages as shown above. If you want to get best in-class automated tracing of your model calls you can also set your LangSmith API key by uncommenting below: 
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

​
Initialization

# | output: false
# | echo: false
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

/Users/ovcharuk/opensource/langchain/.venv/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

from langchain_ydb.vectorstores import YDB, YDBSearchStrategy, YDBSettings

settings = YDBSettings(
    table="ydb_example",
    strategy=YDBSearchStrategy.COSINE_SIMILARITY,
)
vector_store = YDB(embeddings, config=settings)

​
Manage vector store

Once you have created your vector store, you can interact with it by adding and deleting different items.

​
Add items to vector store

Prepare documents to work with: 
from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]
You can add items to your vector store by using the add_documents function. 
vector_store.add_documents(documents=documents, ids=uuids)

Inserting data...: 100%|██████████| 10/10 [00:00<00:00, 14.67it/s]

['947be6aa-d489-44c5-910e-62e4d58d2ffb',
 '7a62904d-9db3-412b-83b6-f01b34dd7de3',
 'e5a49c64-c985-4ed7-ac58-5ffa31ade699',
 '99cf4104-36ab-4bd5-b0da-e210d260e512',
 '5810bcd0-b46e-443e-a663-e888c9e028d1',
 '190c193d-844e-4dbb-9a4b-b8f5f16cfae6',
 'f8912944-f80a-4178-954e-4595bf59e341',
 '34fc7b09-6000-42c9-95f7-7d49f430b904',
 '0f6b6783-f300-4a4d-bb04-8025c4dfd409',
 '46c37ba9-7cf2-4ac8-9bd1-d84e2cb1155c']

​
Delete items from vector store

You can delete items from your vector store by ID using the delete function. 
vector_store.delete(ids=[uuids[-1]])

True

​
Query vector store

Once your vector store has been created and relevant documents have been added, you will likely want to query it during the execution of your chain or agent.

​
Query directly

A simple similarity search can be performed as follows: 
results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy", k=2
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

​
Similarity search with score

You can also perform a search with a score: 
results = vector_store.similarity_search_with_score("Will it be hot tomorrow?", k=3)
for res, score in results:
    print(f"* [SIM={score:.3f}] {res.page_content} [{res.metadata}]")

* [SIM=0.595] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]
* [SIM=0.212] I had chocolate chip pancakes and scrambled eggs for breakfast this morning. [{'source': 'tweet'}]
* [SIM=0.118] Wow! That was an amazing movie. I can't wait to see it again. [{'source': 'tweet'}]

​
Filtering

You can search with filters as described below: 
results = vector_store.similarity_search_with_score(
    "What did I eat for breakfast?",
    k=4,
    filter={"source": "tweet"},
)
for res, _ in results:
    print(f"* {res.page_content} [{res.metadata}]")

* I had chocolate chip pancakes and scrambled eggs for breakfast this morning. [{'source': 'tweet'}]
* Wow! That was an amazing movie. I can't wait to see it again. [{'source': 'tweet'}]
* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

​
Query by turning into retriever

You can also transform the vector store into a retriever for easier usage in your chains. Here’s how to transform your vector store into a retriever and then invoke the retriever with a simple query and filter. 
retriever = vector_store.as_retriever(
    search_kwargs={"k": 2},
)
results = retriever.invoke(
    "Stealing from the bank is a crime", filter={"source": "news"}
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Robbers broke into the city bank and stole $1 million in cash. [{'source': 'news'}]
* The stock market is down 500 points today due to fears of a recession. [{'source': 'news'}]

​
Usage for retrieval-augmented generation

For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:

​
API reference

For detailed documentation of all YDB features and configurations head to the API reference:python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.ydb.YDB.html
⌘I